[PDF][PDF] 基于深度学习的行人重识别研究进展
罗浩， 姜伟， 范星， 张思朋 - 自动化学报, 2019 - aas.net.cn
摘要行人重识别是计算机视觉领域近年来非常热的一个研究课题, 可以被视为图像检索的一个子
问题, 其目标是给定一个监控行人图像检索跨设备下的该行人图像. 传统的方法依赖手工特征 …
问题, 其目标是给定一个监控行人图像检索跨设备下的该行人图像. 传统的方法依赖手工特征 …
Visible-infrared person re-identification via homogeneous augmented tri-modal learning
Matching person images between the daytime visible modality and night-time infrared
modality (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing …
modality (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing …
Describing video with attention-based bidirectional LSTM
Video captioning has been attracting broad research attention in the multimedia community.
However, most existing approaches heavily rely on static visual information or partially …
However, most existing approaches heavily rely on static visual information or partially …
Cross-modality interactive attention network for multispectral pedestrian detection
Multispectral pedestrian detection is an emerging solution with great promise in many
around-the-clock applications, such as automotive driving and security surveillance. To …
around-the-clock applications, such as automotive driving and security surveillance. To …
Dynamic graph co-matching for unsupervised video-based person re-identification
Cross-camera label estimation from a set of unlabeled training data is an extremely
important component in the unsupervised person re-identification (re-ID) systems. With the …
important component in the unsupervised person re-identification (re-ID) systems. With the …
Coarse-to-fine UAV target tracking with deep reinforcement learning
W Zhang, K Song, X Rong, Y Li - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
The aspect ratio of a target changes frequently during an unmanned aerial vehicle (UAV)
tracking task, which makes the aerial tracking very challenging. Traditional trackers struggle …
tracking task, which makes the aerial tracking very challenging. Traditional trackers struggle …
Learning modality-consistency feature templates: A robust RGB-infrared tracking system
With a large number of video surveillance systems installed for the requirement from
industrial security, the task of object tracking, which aims to locate objects of interest in …
industrial security, the task of object tracking, which aims to locate objects of interest in …
SCRATCH: A scalable discrete matrix factorization hashing framework for cross-modal retrieval
In this paper, we present a novel supervised cross-modal hashing framework, namely
Scalable disCRete mATrix faCtorization Hashing (SCRATCH). First, it utilizes collective …
Scalable disCRete mATrix faCtorization Hashing (SCRATCH). First, it utilizes collective …
Video person re-identification by temporal residual learning
In this paper, we propose a novel feature learning framework for video person re-
identification (re-ID). The proposed framework largely aims to exploit the adequate temporal …
identification (re-ID). The proposed framework largely aims to exploit the adequate temporal …
Exploring discriminative representations for image emotion recognition with CNNs
W Zhang, X He, W Lu - IEEE Transactions on Multimedia, 2019 - ieeexplore.ieee.org
Image emotion recognition aims to automatically categorize the emotion conveyed by an
image. The potential of deep representation has been demonstrated in recent research on …
image. The potential of deep representation has been demonstrated in recent research on …